English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automated multi-document extractive text summarization is a widely studiedresearch problem in the field of natural language understanding. Suchextractive mechanisms compute in some form the worthiness of a sentence to beincluded into the summary. While the conventional approaches rely on humancrafted document-independent features to generate a summary, we develop adata-driven novel summary system called HNet, which exploits the varioussemantic and compositional aspects latent in a sentence to capture documentindependent features. The network learns sentence representation in a way that,salient sentences are closer in the vector space than non-salient sentences.This semantic and compositional feature vector is then concatenated with thedocument-dependent features for sentence ranking. Experiments on the DUCbenchmark datasets (DUC-2001, DUC-2002 and DUC-2004) indicate that our modelshows significant performance gain of around 1.5-2 points in terms of ROUGEscore compared with the state-of-the-art baselines.

Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization